© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 12425
    Prev
    Next
    INDEX
    Explanations

    java code syntax, specifically related to class and method definitions

    oai_token-act-pair · gemini-2.0-flash

    Java code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    XmlEnum
    -0.64
    ftagPool
    -0.59
    μβρίου
    -0.59
     مشين
    -0.58
     betweenstory
    -0.56
    ConstraintMaker
    -0.54
     通販
    -0.54
    jet
    -0.52
    GraphicsUnit
    -0.51
    PropertyChanging
    -0.50
    POSITIVE LOGITS
    Véxase
    0.62
     näm
    0.52
     hänen
    0.51
    WithIOException
    0.47
    izioni
    0.46
     possesso
    0.45
    WindowConstants
    0.44
    niająca
    0.44
     demais
    0.43
     peggio
    0.42
    Activations Density 0.156%

    No Known Activations